Information processing device, information processing method, and program for supporting health services.

Abstract

This provides useful information to help health insurers and other organizations conducting health programs implement effective measures. [Solution] The program relating to this disclosure is a program that causes a computer to function as an information processing device for supporting a health business, wherein the information processing device includes: prediction means for predicting the health risk of each of the multiple subjects from the health information of the multiple subjects; evaluation means for dividing the multiple subjects into two or more groups with respect to measures for the health business, determining the health risk of each of the two or more groups, and evaluating the health risk of the two or more groups; and presentation information generation means for generating presentation information to present to the user the effects of the measures for the health business based on the evaluation means.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program for supporting the health care business.

Background Art

[0002] Based on the guidelines for formulating a data health plan provided by the Ministry of Health, Labour and Welfare, insurers (insurers such as national health insurance associations, health insurance associations, and the late-stage elderly medical system, hereinafter referred to as "insurers") are required to formulate common evaluation indicators and describe methods for setting and achieving goals such as outcomes. (Non-Patent Documents 1 to 3). Examples of outcomes include the rate of implementation of specific health checkups, the rate of implementation of specific health guidance, the reduction rate of specific health guidance targets by specific health guidance, the proportion of those with HbA1c of 8.0% or more, the proportion of those with exercise habits, among the elderly in the previous period, the proportion of those with a BMI of 20 kg / m 2 The following proportions, the proportion of those with good chewing ability among those aged 50 to 74 years, etc.

[0003] In Patent Document 1, a system has been proposed that creates a model based on health check information including measurement values of health checkups, receipt information including medical expenses and disease names, and extracts subjects with a high risk of onset based on the health check information of the subjects.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Non-Patent Documents

[0005]

Non-Patent Document 1

Non-Patent Document 2

[0006] The system proposed in Patent Document 1 can identify high-priority individuals for health guidance. However, it could not quantitatively evaluate to what extent achieving the outcomes would extend the average period of independence for members, to what extent it could optimize medical expenses related to lifestyle-related diseases and long-term care benefits, or to what extent it could prevent the onset and progression of dementia, nor could it suggest effective measures that insurers conducting health programs should take.

[0007] This invention has been made in view of the above problems, and its purpose is to realize a technology that can provide useful information to insurers and others who conduct health programs in order to implement effective measures. [Means for solving the problem]

[0008] To solve this problem, for example, the program relating to this disclosure is a program that causes a computer to function as a means of an information processing device that supports a health business, wherein the information processing device comprises: prediction means for predicting the health risk of each of the multiple subjects from the health information of the multiple subjects; evaluation means for dividing the multiple subjects into two or more groups with respect to measures for the health business, determining the health risk of each of the two or more groups, and evaluating the health risk of the two or more groups; and presentation information generation means for generating presentation information to present to the user the effects of the measures for the health business based on the evaluation means. [Effects of the Invention]

[0009] According to the present invention, it becomes possible to provide useful information to insurers and others who conduct health programs in order to implement effective measures. [Brief explanation of the drawing]

[0010] [Figure 1] A diagram showing an example of a health promotion support system according to an embodiment of the present invention. [Figure 2] A block diagram showing an example of the functional configuration of the information processing device according to the embodiment. [Figure 3] A block diagram showing an example of the functional configuration of a terminal device according to this embodiment. [Figure 4] A diagram illustrating an example of the functional configuration of a health information database according to this embodiment. [Figure 5] A flowchart illustrating a series of processes related to health support according to the embodiment. [Figure 6] A flowchart illustrating the process of generating a predictive model according to the embodiment. [Figure 7] A diagram illustrating the process of generating a predictive model according to the embodiment. [Figure 8] A diagram illustrating the operation of the prediction model according to the embodiment. [Figure 9] A flowchart illustrating the process for evaluating the effectiveness of a health program according to the embodiment. [Figure 10]A diagram for explaining the improvement of care risk before and after improvement by the healthcare business according to the embodiment. [Figure 11] A setting screen for evaluating the effect of the healthcare business according to the embodiment. [Figure 12] A presentation screen for presenting the effect of the healthcare business according to the embodiment. [Figure 13] A presentation screen visualizing the effect of extending the average independent period for each goal of the healthcare business in a certain area according to the embodiment. [Figure 14] A presentation screen visualizing the effect of healthcare guidance for each individual according to the embodiment.

Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims, and not all combinations of the features described in the embodiments are essential for the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Also, the same or similar configurations are assigned the same reference numerals, and duplicate descriptions are omitted.

[0012] <Configuration of the Healthcare Business Support System> Referring to FIG. 1, the configuration of the healthcare business support system according to an embodiment of the present invention will be described. The healthcare business support system 100 includes, for example, an information processing device 101, a database 102, and a terminal device 103 used by a user. Here, the user is assumed to be an employee such as an insurer, but is not limited thereto. The information processing device 101, the healthcare information database 102, and the terminal device 103 are communicably connected by a network 104. The network may be any network such as a LAN, a WAN, or the Internet. Also, all or part of the network may be a wireless communication connection.

[0013] <Configuration of the Information Processing Device> The information processing device 101 is, for example, a server managed by an insurer, or a server managed by a company that provides data health services to an insurer. In the following explanation, insurers, local governments, and service providers will not be specifically distinguished and will be referred to simply as "insurers, etc."

[0014] The terminal device 103 is a user terminal for accessing the information processing device 101, for example, when an insurer or the like obtains information related to health guidance. In this embodiment, the case where the terminal device 103 is a desktop computer will be described as an example. However, the terminal device 103 is not limited to a desktop computer, but may be any other device that can access the information processing device 101, such as a notebook computer, a tablet computer, or a smartphone.

[0015] The health information database 102 is a database that stores data related to various types of health information. Health information may include, for example, health checkup data, medical treatment data, prescription claim data, and long-term care certification data, but it does not have to include all of these, and may also include other information. There may be multiple health information databases 102 for each type of data, or there may be only one. The health information database 102 may be owned by insurers, etc., or by other organizations. It may be the National Database of Medical Claims and Specific Health Checkups (NDB) provided by the Ministry of Health, Labour and Welfare, a database owned by a claims processing and payment organization (such as the Social Insurance Medical Fee Payment Fund, the National Health Insurance Association, and the National Health Insurance Federation) (such as KDB), or other databases owned by private companies. Furthermore, the information processing device 101 may also have a database.

[0016] <Functional Configuration of Information Processing Devices> Next, an example of the functional configuration of the information processing device 101 will be described with reference to Figure 2. Note that each of the functional blocks described may be integrated or separated, and the functions described may be implemented in other blocks. Furthermore, what is described as hardware may be implemented in software, and vice versa.

[0017] The communication unit 201 includes a communication circuit that communicates with various devices via a network. The communication unit 201 receives information processed by the control unit 204 from the communication partner device (e.g., terminal device 103) and transmits information processed by the control unit 204 to the communication partner device (e.g., terminal device 103). The power supply unit 202 is a power supply that provides the power necessary for the operation of the information processing device 101.

[0018] The storage unit 203 includes, for example, a non-volatile storage medium such as a hard disk or semiconductor memory, and includes various programs executed by the control unit 204 of the information processing device 101, various data used by the control unit 204, and DB 230. The various programs include programs for performing support for the health business according to this embodiment, as well as an operating system, framework, libraries, etc. The various data include, for example, setting values ​​of the information processing device 101, data obtained from the health information database 102, data related to the prediction model, training data, and prediction result data. The storage unit 203 also stores parameters for each prediction model. Data obtained from the health information database 102 may be stored in DB 230.

[0019] The control unit 204 includes a central processing unit (CPU) 210 and RAM 211. The control unit 204 controls the operation of various parts within the control unit 204 and the operation of various parts of the information processing device 101 by loading and executing programs stored in the memory unit 203 into the RAM 211. The control unit 204 also performs prediction and evaluation of the effects of health programs, which will be described later.

[0020] RAM211 includes a volatile storage medium such as DRAM, and temporarily stores parameters and processing results for the control unit 204 to execute the program.

[0021] The control unit 204 has a functional block that is implemented by the CPU 210 reading a program stored in the memory unit 203 into the RAM 211. The control unit 204 also has functional blocks for a prediction model unit 220, an evaluation unit 221, a learning unit 222, a data acquisition unit 223, a user interface (IF) unit 224, and a presentation information generation unit 225.

[0022] The prediction model unit 220 uses a prediction model to predict an individual's future health status. For example, the long-term care risk prediction model has the function of inputting data from the health information database 102 into the prediction model and outputting the long-term care risk (probability) for the following year.

[0023] The evaluation unit 221 evaluates the effectiveness of measures taken by insurers, etc., based on the prediction results of the prediction model unit 220. For example, it evaluates how much the average period of independence in the future can be extended and how much medical expenses can be reduced by encouraging people to undergo health checkups. The average period of independence is an indicator of the remaining period during which independent living can be expected.

[0024] The learning unit 222 trains the predictive model. It generates and trains the predictive model using data obtained from the health information database 102.

[0025] The data acquisition unit 223 acquires data necessary for prediction and evaluation from the health information database 102 and other data sources. The data acquisition unit 223 may store the acquired data in the DB 230 of the storage unit 203.

[0026] The user interface unit 224 functions as an interface with the terminal device 103 of the insurer, etc. The user interface unit 224 displays an input screen and a settings screen to the terminal device 103 and receives data input from the terminal device 103.

[0027] The information generation unit 225 generates information that visualizes and shows to the user the prediction results from the prediction model and the evaluation of the effectiveness of countermeasures by insurers, etc., by the evaluation unit 221. The generated information is transmitted to the terminal device 103 by the user interface unit 224 and the communication unit 201, and is displayed on the display unit 304 of the terminal device 103.

[0028] <Terminal device configuration> An example of the functional configuration of the terminal device 103 for insurers, etc., will be explained with reference to Figure 3. Note that each of the functional blocks described may be integrated or separated, and the functions described may be implemented in other blocks. Furthermore, what is described as hardware may be implemented in software, and vice versa.

[0029] The communication unit 301 includes, for example, a communication circuit, and communicates with the information processing device 101 via mobile communication such as wired LAN or LTE, or via wireless communication such as WiFi, to send and receive necessary data.

[0030] The operation unit 303 includes buttons and a touch panel provided by the communication device 103, and accepts operations from users such as insurers to display information related to health programs. The display unit 304 includes a display panel such as an LCD or OLED, and displays a GUI for various operations. For example, the display unit 304 displays information generated by the information generation unit 225 of the information processing device 101.

[0031] The storage unit 305 includes, for example, non-volatile memory such as an HDD or semiconductor memory, and stores programs and the like that the control unit 502 executes.

[0032] The control unit 302 includes a CPU 310 and RAM 311. For example, the CPU 310 executes a program stored in the memory unit 305 to control the operation of each functional block within the control unit 302 and each part within the communication device 103.

[0033] <Structure of the health information database> Next, with reference to Figure 4, an example of the functional configuration of the health information database 102 will be described. The health information database 102 is a database server that stores various health information data according to this embodiment. The health information database 102 includes health checkup data 420, dental checkup data 430, medical treatment data 440, prescription claim data 450, long-term care certification data 460, and intervention data 470. The health information database 102 does not have to include all of these, and may also include other medical and health-related data. Each piece of data is recorded for each patient (insured person) and associated with the date on which they received a diagnosis, etc. Medical treatment data 440 and prescription claim data 450 can be obtained from medical fee claim data. Medical treatment data 440 can be obtained from medical claim, dental claim, and long-term care claim data. Medical claim, dental claim, and long-term care claim data are created separately for each patient, each month of treatment, and separately for inpatient and outpatient care. In recent years, with the use of My Number cards as health insurance cards, medical claim data is recorded in association with My Number (individual number). As a result, My Number makes it possible to obtain comprehensive data related to individual medical information, including health checkup data 420, dental checkup data 430, medical treatment data 440, prescription claim data 450, and long-term care certification data 460, as well as vital data obtained from wearable devices, electronic medical record data, etc.

[0034] Furthermore, the health information database 102 may acquire and utilize data from the Ministry of Health, Labour and Welfare's claims information and specific health checkup information database (NDB), databases held by review and payment organizations (such as the Social Insurance Medical Fee Payment Fund, the National Health Insurance Association, and the National Health Insurance Federation) (such as KDB), and other databases held by private companies. Alternatively, the health information database 102 may be NDB, KDB, or other databases held by private companies. In NDB, patient (insured person) information is anonymized, but different types of patients are linked by the same hash ID. Also, the data acquisition unit 223 of the information processing device 101 may be configured to access NDB and acquire data. The learning unit 222 and evaluation unit 221 of the information processing device 101 can use data from NDB, KDB, and other databases.

[0035] The following explains each of the data points. Health checkup data 420 is data from health examinations in a given population. Local governments and corporate health insurance associations conduct health examinations for residents and members. The population of health checkup data 420 may be a single local government or a single company. Alternatively, the population of health checkup data 420 may be multiple local governments or multiple companies. In the following explanation, we will use an example where the insurer is a company that provides health guidance services and uses health checkup data 420 after obtaining permission to use it from multiple local governments and multiple health insurance associations. The same applies to the populations of dental checkup data 430, medical treatment data 440, prescription claim data 450, and long-term care certification data 460 described below.

[0036] Health checkup data 420 is data accumulated annually, linked to the individual, based on the health checkups received by the target group. Health checkup data 420 stores information such as whether or not a target group received a health checkup, and the measured values ​​for each item of the checkup. Health checkup data 420 includes questionnaire data that the target group answers in advance of the health checkup. Health checkup data includes specific health checkup data, which is data on the results of health checkups conducted for target groups aged 40 to 74 focusing on metabolic syndrome, and late-stage elderly health checkup data, which is conducted for target groups aged 75 and over. It may also include health checkup data conducted by employers for their employees in accordance with the Industrial Safety and Health Act. Health checkup data 420 includes data such as examinee information, specific health checkup result information, questionnaire information (medication and smoking history, etc.), determination of eligibility for metabolic syndrome criteria, and determination of eligibility for specific health guidance. Of the 420 health checkup data from the subjects, specific health checkup items included health questions (medication history, smoking history), questionnaires, physical measurements (height, weight, BMI, waist circumference), physical examination, urinalysis (urinary glucose, urinary protein), blood tests (lipids (triglycerides, HDL cholesterol, LDL cholesterol), glucose metabolism (fasting blood glucose or hemoglobin A1C), and liver function (GOT, GPT, γ-GTP)). Additional items included anemia tests (red blood cell count, hemoglobin level, hematocrit), electrocardiogram, fundus examination, and renal and urinary tract examinations.

[0037] Dental checkup data 430 is dental checkup data accumulated annually and associated with the target individuals. Dental checkup data 430 may also include data from regular checkups and specific health checkups. Dental checkup data 430 stores whether the target individuals underwent a dental checkup or not, and the results for each item of the dental checkup. Dental checkup data 430 includes questionnaire data that the target individuals answered during the dental checkup.

[0038] Medical data 440 is data recording the patient's visits, admissions, and discharges from medical institutions. It can be obtained from medical and dental claims data created separately for inpatients and outpatients. Medical data 440 includes the name of the medical institution, visit history, date of treatment, and name of medical procedure.

[0039] The prescription data 450 includes information about the medication dispensed at the pharmacy, information about the prescribing source, and information about the patient. The prescription data 450 is linked to each patient. The prescription data 450 includes the name of the medical institution / pharmacy, the date of dispensing, the name of the drug, the name of the active ingredient, the usage, and the dosage.

[0040] The 460 Care Needs Assessment Data set contains data related to care needs assessment. Care needs assessment is determined by a care needs assessment review committee attached to a local government. Based on the application for assessment, the committee calculates the standard care needs assessment time for five areas (direct assistance with daily living, indirect assistance with daily living, BPSD-related activities, functional training-related activities, and medical-related activities), and then determines the level of support needs (levels 1 to 5) based on the sum of these time and the dementia allowance. The 460 Care Needs Assessment Data set may also include data indicating "independence," which means not needing assistance such as care services to carry out daily life. Furthermore, the 460 Care Needs Assessment Data set may also include data indicating support needs.

[0041] Intervention data 470 includes data recording measures implemented by insurers, etc., with the implementer, date of implementation, and content associated with them, as well as personal medical data obtainable from electronic medical records and vital data obtainable from wearable devices, etc. Interventions can be individual or group. An example of an individual intervention is specific health guidance for people with metabolic syndrome or those at risk of metabolic syndrome. An example of a group intervention is encouraging people who have not undergone health checkups to do so, and health promotion initiatives by insurers, etc. This health business support system handles both group and individual interventions.

[0042] <Machine learning model> In this embodiment, a machine learning model may be used as the predictive model for predicting the effectiveness of health programs. Various data from the health information database 102 are used as explanatory variables. The data used in the health information database 102 may be some types of data or all types of data.

[0043] The target variables for the machine learning model include effects such as extending the average period of independence, delaying the onset of dementia, optimizing medical expenses, optimizing long-term care benefit expenses, preventing lifestyle-related diseases, and improving laboratory test results.

[0044] <Outcomes> Next, the outcome evaluation in this embodiment will be explained. Outcome evaluation refers to the evaluation of the achievement status of the goals of the health program, and specifically, it is the evaluation of the degree of achievement of each item related to the implementation results of the program as shown in the evaluation indicators. The goals include the aforementioned effects of extending healthy life expectancy, delaying the onset of dementia, optimizing medical expenses, optimizing long-term care benefit expenses, preventing lifestyle-related diseases, and improving test results, and the indicators that represent these goals are called outcomes. For example, outcomes are specific indicators that serve as goals, such as improving the status of individuals who are malnourished to a state where they are not malnourished, or reducing the BMI from 25 or higher to less than 25. In outcome evaluation, the extent to which the outcomes set at the planning stage were achieved is evaluated retrospectively. Outcomes include individual-level outcomes and group-level outcomes. In this embodiment, we mainly deal with group-level outcomes, but it is also applicable to individual-level outcomes.

[0045] <Overall flow of this system> Referring to Figure 5, the overall flow of this embodiment will be explained. The flowchart in Figure 5 is realized when the CPU 210 of the information processing device 101 reads the program stored in the memory unit 203 into the RAM 211 and executes it. Hereafter, the step numbers of each process included in the flowchart are indicated by numbers starting with "S". The same applies to subsequent flowcharts.

[0046] In S501, the learning unit 222 of the information processing device 101 generates a predictive model. The predictive model takes health checkup data and other information for an individual and outputs the probability of developing a disease or other condition in the future. Details of S501 will be described later.

[0047] Next, in S502, the prediction model unit 220 of the information processing device 101 uses a prediction model to obtain the future health risks of individuals in a given population as probabilities. Based on the future health risks of individuals obtained by the prediction model unit 220, the evaluation unit 221 evaluates the effectiveness of measures taken by the health program. For example, it evaluates how much the risk of developing diseases, etc., can be reduced by taking measures through the health program for a certain group of target individuals. Details of S502 will be described later. Target individuals are residents if the insurer is a local government, and insured persons or members if it is a health association. Here, target individuals refer to those whom the insurer targets for the health program.

[0048] Finally, in S503, the information display generation unit 225 of the information processing device 101 generates information for evaluating the effectiveness of the health program. The user interface unit 224 then transmits the generated information to the terminal device 103. The terminal device 103 displays the information on the display unit 304. By reviewing the information displayed to show the evaluation results, insurers and others can determine which measures are effective. Details of S503 will be described later.

[0049] <Generating a predictive model> Details of S501 in Figure 5 will be explained with reference to Figures 6 to 8. First, as an example, the effect of extending the mean independent period will be used to explain the generation of the predictive model, referring to the flowchart in Figure 6 and the relationship between data and the model in Figure 7. The flowchart in Figure 6 is realized when the CPU 210 of the information processing device 101 reads the program stored in the memory unit 203 into the RAM 211 and executes it. Here, healthy life expectancy is evaluated by the mean independent period, but healthy life expectancy may also be evaluated by other indicators. Healthy life expectancy is also sometimes called healthy remaining life expectancy or active remaining life expectancy. Here, health checkup data 420, dental checkup data 430, medical treatment data 440, and prescription claim data 450 from the health information database 102 are used as training data, but data can be appropriately selected from the health information database 102.

[0050] In S601, the data acquisition unit 223 of the information processing device 101 acquires health checkup data 420, dental checkup data 430, medical treatment data 440, and prescription claim data 450 for fiscal year 2021 from the health information database 102 and stores them in the storage unit 203.

[0051] Next, in S602, the data acquisition unit 223 of the information processing device 101 acquires the long-term care certification data 470 for fiscal years 2021 and 2022 from the health information database 102 and stores it in the storage unit 203.

[0052] Next, in S603, the learning unit 222 of the information processing device 101 uses the population data from the health checkup data 420, dental checkup data 430, medical treatment data 440, and prescription claim data 450 for fiscal year 2021, excluding data on individuals who have received long-term care certification.

[0053] Next, in S604, the learning unit 222 identifies individuals from the population who newly became classified as requiring Level 2 or higher care in fiscal year 2022. Here, we specify Level 2 or higher care, but it could also be Level 1 or higher care, or Level 3 or higher care. It could also be at the level of requiring support. Furthermore, data on physical frailty may also be included.

[0054] Next, the learning unit 222 trains a predictive model on the patterns of health checkup values, questionnaires, medical history, and prescribed medications from fiscal year 2021 for individuals who newly became classified as requiring care level 2 or higher in fiscal year 2022, based on the aforementioned population. This allows the predictive model to learn which characteristics indicate a high risk of requiring care. While the known gradient boosting algorithm is used for learning, it is not limited to this method.

[0055] The above prediction model was trained using health data from fiscal years 2021 and 2022, but any fiscal year's health data can be used. Furthermore, the period is not limited to fiscal years; it can be a calendar year or a period of two years or more. It can also be in months or periods of several months.

[0056] The questionnaire data included in health checkup data 420 contains information on the subjects' responses to items such as whether or not they use medication, including blood pressure lowering drugs, insulin injections or blood sugar lowering drugs, cholesterol lowering drugs, medical history such as stroke, heart disease, and renal failure, smoking habits, weight gain since age 20, exercise habits, eating habits, drinking habits, and sleep status. Since the information in this questionnaire data is self-reported by the subjects, it can be used as an indicator for creating predictive models and evaluating the effectiveness of health programs.

[0057] Figure 8 shows the operation of the predictive model generated by the learning unit 222. The predictive model for long-term care risk generated by the flow in Figure 6 takes health checkup data, dental checkup data, medical treatment data, and prescription claim data for a given person for a given year as input and outputs the long-term care risk (risk of becoming a Level 2 or higher care recipient) for that person within one year. The input and output of the predictive model do not necessarily have to match the training data used to train the predictive model. For example, the predictive model could be trained using 5 years of data, and then health information for a given person at a certain time could be input to output the long-term care risk for the following year (within one year).

[0058] <Dementia Risk Prediction Model> For the predictive model that forecasts dementia risk, the learning unit 222 will train the predictive model using clinical data, instead of long-term care certification data, for individuals who did not have a confirmed diagnosis of dementia in FY2021 but received a confirmed diagnosis of dementia in FY2022, treating them as newly diagnosed dementia patients. Alternatively, training may also be conducted based on the severity of dementia or the degree of cognitive impairment.

[0059] <Lifestyle-related disease risk prediction model> For predictive models that predict the risk of lifestyle-related diseases, the learning unit 222 uses medical data instead of long-term care certification data to train the predictive model on individuals who were not hospitalized for lifestyle-related diseases in FY2021 but were hospitalized for lifestyle-related diseases in FY2022, treating them as newly hospitalized individuals with lifestyle-related diseases. Alternatively, the predictive model may be trained on individuals who were not treated for lifestyle-related diseases in FY2021 but were treated for lifestyle-related diseases in FY2022, treating them as newly diagnosed individuals with lifestyle-related diseases. Furthermore, by comparing medical expenses related to lifestyle-related diseases between FY2021 and FY2022, the predictive model may be trained on individuals who showed an increase of a certain amount or a certain percentage, treating them as newly diagnosed individuals with lifestyle-related diseases or individuals whose lifestyle-related diseases worsened.

[0060] <Evaluation of the effectiveness of health programs> Referring to Figure 9, the detailed processing of S502 in Figure 5 will be explained. The flowchart in Figure 9 is realized when the CPU 210 of the information processing device 101 reads the program stored in the memory unit 203 into the RAM 211 and executes it.

[0061] This section explains the process of evaluating the extension of the average period of independent living as part of the assessment of the effectiveness of health programs. If the average period of independent living can be extended, insurers can reduce long-term care benefit costs and medical expenses. The evaluation of the effectiveness of health programs is necessary to consider whether insurers can effectively extend the average period of independent living by implementing health programs as a countermeasure.

[0062] By using a long-term care prediction model, it is possible to input health checkup data, dental checkup data, medical treatment data, and prescription claim data for a given year and calculate the risk (probability) of needing long-term care in the following year (within one year).

[0063] Here, the group used to evaluate the extension of the average period of independence does not necessarily have to be the same as the group of subjects used to generate the predictive model for long-term care risk. Generally, accuracy is required when generating predictive models, so a larger amount of data is better. On the other hand, the evaluation of the extension of the average period of independence using the predictive model requires an evaluation that takes into account the size of each local government or health insurance association and the composition of the subjects. Therefore, the target group for evaluation of the extension of the average period of independence is the group that insurers, etc., are targeting for health programs.

[0064] In S901, the prediction model unit 220 of the information processing device 101 uses a long-term care risk prediction model to first input the health information of each individual for all members of the group of target persons such as insurers, and calculate each individual's long-term care risk (probability of becoming a Level 2 or higher care recipient) one year later (within one year).

[0065] Next, in S902, the evaluation unit 221 of the information processing device 101 divides the subjects into two groups, for example, those who have undergone a health checkup and those who have not. The evaluation unit calculates the care risk (probability of becoming a care recipient of level 2 or higher) for the group that has undergone a health checkup and the care risk (probability of becoming a care recipient of level 2 or higher) for the group that has not undergone a health checkup by taking the average of the care risk (probability of becoming a care recipient of level 2 or higher) for the subjects in each group. Here, the subjects are divided into two groups, but there may be three or more groups. Also, although the average of the probabilities of the subjects within each group is taken, other values ​​such as the median or mode may also be used. As a result of taking the average, the care risk (probability of becoming a care recipient of level 2 or higher) for the group that has undergone a health checkup is 1.0%, and the care risk (probability of becoming a care recipient of level 2 or higher) for the group that has not undergone a health checkup is 3.0%.

[0066] Next, in S903, the evaluation unit 221 of the information processing device 101 calculates the difference between the care risk (probability of becoming a care recipient of level 2 or higher) of 3.0% for the group that did not undergo health checkups and the care risk (probability of becoming a care recipient of level 2 or higher) of 1.0% for the group that did undergo health checkups. In this case, the difference is 2.0%. This difference means that if everyone who has not undergone a health checkup were to undergo one, the care risk (probability of becoming a care recipient of level 2 or higher) would decrease by 2.0%.

[0067] Next, in S904, the evaluation unit 221 of the information processing device 101 calculates the percentage decrease in the average value. In the example above, the difference in the average value is considered to be the decrease in the average value of the risk of requiring care level 2 or higher. If the group that did not undergo health checkups starts undergoing health checkups, it is assumed that the probability of requiring care level 2 or higher decreases from 3.0% to 1.0%, resulting in a 66.7% reduction in the risk of requiring care. Therefore, it is evaluated that the risk of requiring care improved by 66.7% by having subjects who did not undergo health checkups undergo health checkups.

[0068] In S903, the difference in group probabilities was obtained, and in S904, the improvement was evaluated based on the ratio of the difference to the probability when no countermeasures were taken. However, it is also possible to evaluate by calculating the ratio between groups without using the difference.

[0069] Next, in S905, the information processing device 101 determines whether there are other groupings. In this example, the groups were determined by whether or not a health checkup was received, but various other groupings are possible, such as whether or not a dental checkup was received, or whether or not there are underlying diseases. If there are no other groupings (YES), the process ends. If there are other groupings (NO), the process in S902 to S904 is repeated for the other groupings.

[0070] Next, in S906, for example, the information display generation unit 225 of the information processing device 101 generates information to visualize and show the user that if the group that has not undergone health checkups starts undergoing health checkups, the risk of needing long-term care will decrease by 66.7%. If there are other group divisions, the same information display is generated. The generated information display can be stored in the storage unit 203 of the information processing device 101. The generated information display is also provided to the terminal device 103 of the insurer, etc., via the user interface unit 224 and the communication unit 201, and is presented to the user.

[0071] The grouping for evaluation conducted by the evaluation unit 221 is related to health programs. For example, whether or not a person has received a health checkup can lead to measures by insurers, etc., to encourage those individuals to receive health checkups and to implement health programs. These measures may also involve intervention by insurers, etc., with their insured individuals.

[0072] <Acquisition of the average extension of the period of independence> The evaluation unit 221 of the information processing device 101 also performs predictive processing such as the extension of the average period of independence. By having individuals who have not received health checkups undergo health checkups, the incidence of requiring long-term care decreases by 66.7%. Assuming that this reduction continues until age 75 or older, the evaluation unit 221 calculates the remaining average period of independence in two scenarios: one where health checkups are not received and one where health checkups are received, and defines the difference as the extension of the average period of independence.

[0073] The information generation unit 225 may generate a graph, such as the one shown in Figure 10, that shows the change in the care risk of the subject when they do not undergo health checkups and when they start undergoing health checkups.

[0074] Figure 10 shows the average caregiving risk for individuals who do not undergo health checkups and the average caregiving risk for individuals who do undergo health checkups. It indicates that the caregiving risk improves when individuals who previously did not undergo health checkups begin to do so. This caregiving risk can be used to evaluate the extension of the average remaining independent period at each age when health programs are implemented.

[0075] Strictly speaking, the average remaining independent period calculated using this method is not the direct result of encouraging health checkups, but it can be considered a useful indicator that quantifies the effect. By evaluating the effect of extending the average remaining independent period in this way, it is possible to assess the effectiveness of health programs such as encouraging health checkups conducted by insurers and other organizations.

[0076] Furthermore, extending the average remaining period of independence increases the age at which people require care, thus reducing care benefit costs. The evaluation unit 221 can evaluate the monetary effect of encouraging health checkups by insurers, etc., based on the average amount of care benefit costs paid by insurers, etc., per person per year.

[0077] <Dementia Delay Effect> Let's explain other evaluation examples. For example, this health program support system can be used to evaluate the effect of health programs on delaying the onset of dementia. Regarding dementia, if a subject does not have a confirmed diagnosis of dementia in their medical data for a certain year, but does have a confirmed diagnosis of dementia in their medical data for the following year, it can be said that the subject has newly developed dementia. Alternatively, the assessment of the progression of dementia and the recognition of memory loss may also be performed. Based on the data of these subjects, the learning unit 222 can generate a dementia risk prediction model in the prediction model flow.

[0078] Once a dementia risk prediction model is generated, the prediction model unit 220 can predict the dementia risk of each individual subject as a probability. The evaluation unit 221 divides the target group into two or more groups and obtains the average value of the dementia onset risk (probability) for each individual subject in each group. From the ratio of the difference in the average values ​​of the risks (probabilities), the evaluation unit 221 can predict what kind of intervention can reduce the dementia risk for each group. For example, by dividing the group into those who have received dental checkups and those who have not, the effect of delaying dementia in years can be evaluated by encouraging dental checkups.

[0079] <Effect of reducing medical expenses for lifestyle-related diseases> This health promotion support system allows us to evaluate not only the delay effect but also the effect of reducing medical costs. If a subject's medical data for a given year shows no hospitalizations related to lifestyle-related diseases, but the medical data for the following year shows hospitalizations related to lifestyle-related diseases, then it can be said that the subject has newly developed a lifestyle-related disease. Furthermore, the increase in the subject's medical expenses and the rate of increase can be used to assess the severity of the subject's lifestyle-related disease. Based on this data, the learning unit 222 can generate a lifestyle-related disease risk prediction model in the prediction model generation flow.

[0080] Once a lifestyle-related disease risk prediction model is generated, the prediction model unit 220 can predict the lifestyle-related disease risk of each individual subject as a probability. The evaluation unit 221 divides the target population into two or more groups and obtains the average risk (probability) for each individual subject in each group. From the percentage difference in the average risk, the evaluation unit 221 can predict what kind of intervention would reduce the lifestyle-related disease risk for each group. For example, by dividing people into groups based on whether or not they have an exercise habit, the reduction in lifestyle-related disease risk by encouraging exercise can be evaluated as a percentage.

[0081] Furthermore, the evaluation unit 221 determines that lifestyle-related diseases lead to increased medical expenses, and calculates the average medical expenses per person when a lifestyle-related disease develops. By comparing these medical expenses with and without the recommendation of exercise, the effectiveness of the health promotion program can be evaluated based on the reduction in medical expenses in both cases.

[0082] <Visualization of the effects of health programs> As described above, the health support system of this embodiment can calculate the extension of the average period of independence, the delay in the onset of dementia, the appropriate effect amount on long-term care benefit expenses, and the appropriate effect amount on hospitalization medical expenses for lifestyle-related diseases. In S503 of Figure 5, the effects of candidate health programs to be implemented by insurers, etc. are visualized and presented. By examining the visualized effects of health programs, insurers, etc. can decide which health programs to implement to achieve the desired results.

[0083] Let's explain S503 in Figure 5 in detail. First, referring to Figures 11 and 12, we will explain how the effectiveness of lifestyle-related disease countermeasures and long-term care measures implemented by insurers, etc., is visualized. The setting screen 1100 in Figure 11 and the effect display screen 1200 in Figure 12 are displayed on the display unit 304 of the terminal device 103 of the insurer, etc., by accessing the information processing device 101 from the terminal device 103.

[0084] The settings screen 1100 in Figure 11 is a settings screen where insurers and others input settings to evaluate the effectiveness of health promotion activities. The settings screen 1100 has input items for the target area 1101, the health promotion activity goal 1102, and the number of target people 1103. These inputs can be set on a single screen, or by sequentially switching between multiple screens.

[0085] In setting the target area 1101, the user enters the prefecture and municipality. The target area can also be set at the prefecture level. The user can choose not to select a municipality, or they can select the entire prefecture by selecting "entire" from the options. In the setting screen 1100, a pull-down menu is used, but input is not limited to this; the user can also enter a name or use other selection methods.

[0086] Next, health promotion objectives 1102 are set. In the example in Figure 11, objectives related to lifestyle-related diseases and long-term care measures are set, but this is not limited to these. In the example in Figure 11, items such as making health checkups a habit, reducing BMI from 25.0 or higher to 18.5-24.9, reducing HbA1c from 7.0 or higher to 6.9 or lower, and not letting eGFR of 45-59.9 fall below 45 are set by insurers, etc., according to the health promotion promotion.

[0087] Goal 1102 of the health program includes an item called "Outcomes." In the Outcomes section, it is possible to set 10 outcomes to be addressed in the data health plan. The 10 outcomes that can be set are malnutrition, oral health, polypharmacy, hypnotics, physical frailty, poor control, discontinuation of treatment for diabetes, etc., frailty prevention in patients with underlying diseases, poor renal function, and unknown health status. Other items can also be set as outcomes, not limited to these. Conditions are set for each. For example, malnutrition is defined as having a BMI <= 20 and quality (weight change). Oral health is defined as having poor chewing and swallowing function and not having visited a dentist in the past year. Polypharmacy is defined as having 15 or more prescribed medications. Hypnotics is defined as having been prescribed hypnotics and having a history of falls, or having both cognitive quality 10 (cognitive forgetfulness) and cognitive quality 11 (cognitive disorientation). Physical frailty is a state of physical decline due to aging, an intermediate state between healthy and requiring long-term care. Physical frailty is defined as having poor health, slow walking speed, or a history of falls. Poorly controlled conditions include high blood glucose and blood pressure, but no history of prescriptions for diabetes or hypertension for the past year. Interruption of diabetes treatment is defined as having no health checkup history in the year of selection, but having a history of prescriptions for diabetes or hypertension in the three years prior to the year of selection, and no history of prescriptions in the year of selection. Frailty prevention with underlying disease is defined as being under or having interrupted treatment for diabetes, having cardiovascular disease such as heart failure or stroke, or having high blood glucose levels and poor health status, weight gain, falls, or frequency of going out. Poor renal function is defined as having poor renal function values, detecting proteinuria, and not having sought medical treatment. Individuals with unknown health status are defined as those who have not undergone health checkups in the year of selection or the year prior to selection, have no medical claims (inpatient, outpatient, dental), and have not been certified as requiring long-term care.

[0088] The items in Health Program Goal 1102 correspond to the grouping in the flowchart in Figure 9. For example, the goal of making health checkups a habit is set when you want to consider how effective it is to encourage people who have not had health checkups to get them and make it a habit. Also, the goal of reducing the BMI of people with a BMI of 25.0 or higher to 18.5-24.9 is a goal to reduce the number of obese people, and it is set when you want to consider how effective it is to the operation of health programs, such as how much hospitalizations related to lifestyle-related diseases will decrease and how much medical expenses will be reduced, if measures such as dietary guidance and exercise guidance are taken in health programs to reduce the BMI of people with a BMI of 25.0 or higher to 18.5-24.9. The goal of reducing the HbA1c of people with a BMI of 7.0 or higher to 6.9 or lower is set when you want to consider how effective it is to the operation of health programs, such as dietary guidance and exercise guidance, if measures are taken in health programs to prevent the worsening of diabetes. Furthermore, the goal of preventing individuals with an eGFR of 45-59.9 from falling below 45 is set after considering the expected effect on the operation of health programs, such as dietary guidance, when implemented as part of health programs to maintain kidney function. The setting of health program objective 1102 is not limited to those listed in Figure 11; any arbitrary items can be included.

[0089] The setting for the number of people covered (1103) is where the insurer or other relevant authority sets the number of people covered. Generally, for local governments, this would be the number of residents, and for insurers or other relevant authorities, it would be the number of people covered. The number of people covered does not necessarily have to be everyone; the number of people covered can be varied depending on age or gender. Alternatively, the system could allow input for age groups or gender.

[0090] Figure 12 is the effect display screen 1200, which displays the effects of health program measures according to the targets set by the settings screen 1100. The effect display screen 1200 shows the expected effects over a 5-year period as an example. The prediction period for the effects is not limited to 5 years; it can be 1 year or any other period. Numerical area 1201 shows the effects numerically. Graph area 1202 shows the effects graphically. The effect of reducing lifestyle-related disease medical expenses 1203 shows that compared to the case where no measures were taken by the health program, medical expenses related to lifestyle-related diseases can be reduced by 200,000 thousand yen, representing a 50% reduction in lifestyle-related disease medical expenses. Graph 1206 on the left of graph area 1202 shows the case where no measures were taken by the health program, and graph 1207 on the right shows the case where measures were taken by the health program.

[0091] The effect of reducing long-term care benefit costs (1204) shows that, compared to a scenario where no measures were taken through health programs, the number of people who require Level 2 or higher long-term care decreases, resulting in a reduction of 100,000 thousand yen, or 40%, in long-term care benefit costs. The effect of reducing the number of people requiring Level 2 or higher long-term care (1202) shows that, compared to a scenario where no measures were taken through health programs, the number of people requiring Level 2 or higher long-term care decreases by 50, resulting in a 28% reduction in the number of people requiring Level 2 or higher long-term care.

[0092] <Second Embodiment> Next, a second embodiment will be described. In the first embodiment, goals were set for the health program and the effectiveness of the measures taken for the health program was evaluated. In the first embodiment, the user sets the goals for the health program, but there may be cases where the user has no idea what kind of goals to set. In the second embodiment, a comparison is presented to show which measures would be effective as part of the health program.

[0093] This section describes an example of displaying the effect of extending healthy life expectancy. The information generation unit 225 generates the display screen 1300 shown in Figure 13. The display screen 1300 visualizes and displays the effect of extending healthy life expectancy for each goal of a health program in a certain region. The display screen 1300 visualizes the effect of extending healthy life expectancy at ages 75, 80, and 85 for all or some of the items of the health program goal 1102 shown in Figure 11. The graphs and figures represent the expected extension in years if the measures for each health program are implemented.

[0094] For example, in the case of a 75-year-old man, it can be understood that reducing the number of malnourished men by one through dietary guidance as part of a health program can extend healthy life expectancy by 1.4 years. Furthermore, it can be understood that increasing the BMI from below 18.4 to between 18.5 and 24.9 can extend healthy life expectancy by 1.0 year. Therefore, in this region, insurers and other relevant parties can understand that providing nutritional guidance and dietary advice to men around 75 years old as part of a health program to ensure adequate nutrition and prevent excessive weight loss can be expected to extend healthy life expectancy.

[0095] Users such as insurers can determine their target items based on the display screen 1300 in Figure 13. Once the user enters the determined targets into the settings screen in Figure 11, they can evaluate the reduction effects on medical expenses, long-term care benefit expenses, etc., on the results screen 1200 in Figure 12. This health promotion support system allows users to evaluate which health promotion measures will yield the most effective results.

[0096] <Third Embodiment> Next, a third embodiment will be described. The first and second embodiments evaluated the effectiveness of health promotion measures for the entire group of beneficiaries, such as insurers. The third embodiment presents what kind of health guidance would be effective for each individual beneficiary.

[0097] The display screen 1400 in Figure 14 shows numerically what kind of health guidance would be effective for each individual. The graphs and numbers show the expected extension of each individual's average healthy lifespan if improvements or prevention are implemented in the following areas: regular health checkups, regular dental checkups, improvement of malnutrition, improvement of oral health, improvement of polypharmacy, improvement of sleeping pill use, improvement of physical frailty, improvement of diabetes treatment discontinuation, and prevention of frailty.

[0098] For example, if it is found that improving the use of sleeping pills would extend the healthy lifespan of person A by 1.7 years, then the insurer should provide health guidance to person A regarding the prescription of sleeping pills. This health program support system can evaluate not only the effectiveness of health programs for groups, but also the effectiveness of health guidance for individuals.

[0099] The invention is not limited to the embodiments described above, and various modifications and changes are possible within the scope of the gist of the invention. [Explanation of Symbols]

[0100] 101: Information processing device, 102: Health information database, 103: Terminal device

Claims

1. A program that causes a computer to function as a means of an information processing device that supports health services, wherein the information processing device is A prediction means that predicts the health risk of each of the multiple subjects from the health information of the multiple subjects, Regarding measures for health promotion programs, an evaluation means for dividing the aforementioned multiple target individuals into two or more groups, determining the health risk for each of the two or more groups, and evaluating the health risk for the two or more groups, The system includes a presentation information generation means for generating presentation information to present to the user the effects of the measures taken in the health program based on the evaluation means. program.

2. The health risks of the two or more groups are the average of the health risks of each of the multiple subjects belonging to the two or more groups. The program according to claim 1.

3. The evaluation of the health risk by the evaluation means is performed by evaluating the difference in the health risks of the two or more groups. The program according to claim 1.

4. The prediction made by the prediction means includes at least one of the following: caregiving risk, dementia risk, and lifestyle-related disease risk. The program according to claim 1.

5. The aforementioned health information includes at least one of health checkup data, medical claims data, and prescription claims data. The program according to claim 1.

6. The aforementioned health checkup data includes questionnaire data. The program according to claim 5.

7. The aforementioned prediction means is a predictive model that learns from the health information of subjects whose health status changed from one period to the next. The program according to claim 1.

8. The evaluation by the evaluation means includes at least one of the following: the effect on extending the healthy lifespan or independent period of the subject, the effect on reducing costs, and the effect on the number of people whose health status has improved. The program according to claim 1.

9. The information presented above visualizes the effects of each of the multiple measures mentioned above in the health program. The program according to claim 1.

10. The information presented above visualizes the effectiveness of each of the aforementioned health measures for each of the aforementioned target individuals. The program according to claim 1.

11. An information processing device that supports health services, A prediction means that predicts the health risk of each of the multiple subjects from the health information of the multiple subjects, Regarding measures for health promotion programs, an evaluation means for dividing the aforementioned multiple target individuals into two or more groups, determining the health risk for each of the two or more groups, and evaluating the health risk for the two or more groups, The system includes a presentation information generation means for generating presentation information to present to the user the effects of the measures taken in the health program based on the evaluation means. Information processing device.

12. An information processing method performed by an information processing device that supports health services, A prediction process that predicts the health risks of each of the multiple subjects based on their health information, Regarding measures for health promotion programs, the process includes dividing the aforementioned multiple target individuals into two or more groups, determining the health risk for each of the two or more groups, and evaluating the health risks of the two or more groups, The system includes a presentation information generation step that generates presentation information for presenting to the user the effects of the measures taken in the health program based on the evaluation step. Information processing methods.

Images